相关论文: Mention Annotations Alone Enable Efficient Domain …

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…

Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can…

Vision foundation models have demonstrated exceptional generalization capabilities in segmentation tasks for both generic and specialized images. However, a performance gap persists between foundation models and task-specific, specialized…

Brain MR image segmentation is a key task in neuroimaging studies. It is commonly conducted using standard computational tools, such as FSL, SPM, multi-atlas segmentation etc, which are often registration-based and suffer from expensive…

Most domain adaptation methods focus on single-source-single-target adaptation settings. Multi-target domain adaptation is a powerful extension in which a single classifier is learned for multiple unlabeled target domains. To build a…

Continual pretraining is a popular way of building a domain-specific pretrained language model from a general-domain language model. In spite of its high efficiency, continual pretraining suffers from catastrophic forgetting, which may harm…

Convolutional neural networks (CNNs) have led to significant improvements in the semantic segmentation of images. When source and target datasets come from different modalities, CNN performance suffers due to domain shift. In such cases…

Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews…

Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature…

Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark…

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

Suicidal ideation detection is critical for real-time suicide prevention, yet its progress faces two under-explored challenges: limited language coverage and unreliable annotation practices. Most available datasets are in English, but even…

Cross-domain object detection is challenging, and it involves aligning labeled source and unlabeled target domains. Previous approaches have used adversarial training to align features at both image-level and instance-level. At the instance…

Coreference resolution is an intermediate step for text understanding. It is used in tasks and domains for which we do not necessarily have coreference annotated corpora. Therefore, generalization is of special importance for coreference…

Recently, neural networks have shown promising results for named entity recognition (NER), which needs a number of labeled data to for model training. When meeting a new domain (target domain) for NER, there is no or a few labeled data,…

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper…

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall…

We introduce a fully differentiable approximation to higher-order inference for coreference resolution. Our approach uses the antecedent distribution from a span-ranking architecture as an attention mechanism to iteratively refine span…

Purpose: In medical research, deep learning models rely on high-quality annotated data, a process often laborious and timeconsuming. This is particularly true for detection tasks where bounding box annotations are required. The need to…

High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…